import tensorflow as tf 復制代碼/anaconda3/envs/py35/lib/python3.5/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.from ._conv import register_converters as _register_converters 復制代碼 inputs = tf.placeholder(tf.float32, [None, 10]) 復制代碼output = tf.layers.dense(inputs, 1) 復制代碼output.get_shape() 復制代碼TensorShape([Dimension(None), Dimension(1)]) 復制代碼 inputs = tf.placeholder(tf.float32, [None, 32, 32, 3]) 復制代碼output = tf.layers.conv2d(inputs, 64, 5) 復制代碼output.get_shape() 復制代碼TensorShape([Dimension(None), Dimension(28), Dimension(28), Dimension(64)]) 復制代碼 output = tf.layers.conv2d(inputs, 64, 5, strides=(2,2), padding='same') 復制代碼output.get_shape() 復制代碼TensorShape([Dimension(None), Dimension(16), Dimension(16), Dimension(64)]) 復制代碼 out2 = tf.layers.max_pooling2d(output, 2, 2) 復制代碼out2.get_shape() 復制代碼TensorShape([Dimension(None), Dimension(8), Dimension(8), Dimension(64)]) 復制代碼

總結

以上是生活随笔為你收集整理的Tensorflow tf.layers的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。